You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection

Benchmark Model Rank Results
object-detection-on-coco-oYOLOS-B (ViT-B)#30Average mAP: 20.0Effective Robustness: 1.05
object-detection-on-coco-val2017YOLOS-B#367box AP: 42.0
object-detection-on-coco-val2017YOLOS-S (dwr)#424box AP: 37.6
object-detection-on-coco-val2017YOLOS-Ti#442box AP: 30.0
image-classification-on-imagenetYOLOS-S#695Top 1 Accuracy: 81.2%